{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X223NSX42FHTNXJULXZPBYQKKP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e20a4a5c4c9011698e93716274709c14cf86e2b2abbd758c885330cdaab4db36","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T15:50:21Z","title_canon_sha256":"d41553fea725b7b6aed6a0a6396dbd6a252e1cba2cc33bd5a21ab0b2b2a6f7eb"},"schema_version":"1.0","source":{"id":"2506.18781","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18781","created_at":"2026-07-05T11:25:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18781v1","created_at":"2026-07-05T11:25:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18781","created_at":"2026-07-05T11:25:55Z"},{"alias_kind":"pith_short_12","alias_value":"X223NSX42FHT","created_at":"2026-07-05T11:25:55Z"},{"alias_kind":"pith_short_16","alias_value":"X223NSX42FHTNXJU","created_at":"2026-07-05T11:25:55Z"},{"alias_kind":"pith_short_8","alias_value":"X223NSX4","created_at":"2026-07-05T11:25:55Z"}],"graph_snapshots":[{"event_id":"sha256:568a0a65138c65029e4f8fbf39de4993bb29083623ad8dac91ad8d7142b968c3","target":"graph","created_at":"2026-07-05T11:25:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.18781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have grown increasingly powerful, yet ensuring their decisions remain transparent and trustworthy requires self-consistency -- no contradictions in their internal reasoning. Our study reveals that even on simple tasks, such as comparing points on a line or a plane, or reasoning in a family tree, all smaller models are highly inconsistent, and even state-of-the-art models like DeepSeek-R1 and GPT-o4-mini are not fully self-consistent. To quantify and mitigate these inconsistencies, we introduce inconsistency metrics and propose two automated methods -- a graph-based","authors_text":"Andrew Chi-Chih Yao, Jiawen Tao, Yang Yuan, Zhenru Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T15:50:21Z","title":"Existing LLMs Are Not Self-Consistent For Simple Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18781","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ef0d3e70c26d7e4ef94d1f6b37b639e43a3fc2581752b8fabf2f749808723367","target":"record","created_at":"2026-07-05T11:25:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e20a4a5c4c9011698e93716274709c14cf86e2b2abbd758c885330cdaab4db36","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T15:50:21Z","title_canon_sha256":"d41553fea725b7b6aed6a0a6396dbd6a252e1cba2cc33bd5a21ab0b2b2a6f7eb"},"schema_version":"1.0","source":{"id":"2506.18781","kind":"arxiv","version":1}},"canonical_sha256":"beb5b6cafcd14f36dd345df2f0e20a53e3b6db521d8bdc7e262b07ead56da22d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"beb5b6cafcd14f36dd345df2f0e20a53e3b6db521d8bdc7e262b07ead56da22d","first_computed_at":"2026-07-05T11:25:55.976020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:55.976020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"guWwm3FJCLST32u6VJwU9zACsXYAUDUpPH9HDdKXl1bUnBn/6fyc2wWtOe1Ayq/iX+DU5jJKJJCJy2WZhsnXDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:55.976499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18781","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef0d3e70c26d7e4ef94d1f6b37b639e43a3fc2581752b8fabf2f749808723367","sha256:568a0a65138c65029e4f8fbf39de4993bb29083623ad8dac91ad8d7142b968c3"],"state_sha256":"07cbda48b4f489a97acf623ac2393f20c7f7e72b6fde4709e3109cf81f05a300"}